Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4316 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2582. Min Range: -1.2582

Max Act: 1.2582. Min Act: -0.0000

Data Index: 151008 (The Pile)

Max Activating Token Index: 431

Text #1

Max Range: 1.2582. Min Range: -1.2582

Max Act: 1.0785. Min Act: -0.0000

Data Index: 1042359 (The Pile)

Max Activating Token Index: 859

Text #2

Max Range: 1.2582. Min Range: -1.2582

Max Act: 1.0158. Min Act: 0.0000

Data Index: 1806010 (The Pile)

Max Activating Token Index: 993

Text #3

Max Range: 1.2582. Min Range: -1.2582

Max Act: 1.0782. Min Act: -0.0000

Data Index: 1047297 (The Pile)

Max Activating Token Index: 912

Text #4

Max Range: 1.2582. Min Range: -1.2582

Max Act: 1.0904. Min Act: -0.0000

Data Index: 1716691 (The Pile)

Max Activating Token Index: 394

Text #5

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.9246. Min Act: 0.0000

Data Index: 748936 (The Pile)

Max Activating Token Index: 1012

Text #6

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.9642. Min Act: 0.0000

Data Index: 1876836 (The Pile)

Max Activating Token Index: 535

Text #7

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.9980. Min Act: -0.0000

Data Index: 522909 (The Pile)

Max Activating Token Index: 391

Text #8

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.9822. Min Act: -0.0000

Data Index: 1677089 (The Pile)

Max Activating Token Index: 697

Text #9

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.9023. Min Act: 0.0000

Data Index: 1363857 (The Pile)

Max Activating Token Index: 183

Text #10

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.8838. Min Act: -0.0000

Data Index: 453104 (The Pile)

Max Activating Token Index: 513

Text #11

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.8599. Min Act: -0.0000

Data Index: 1000545 (The Pile)

Max Activating Token Index: 266

Text #12

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.8544. Min Act: -0.0000

Data Index: 1933593 (The Pile)

Max Activating Token Index: 508

Text #13

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.8524. Min Act: -0.0000

Data Index: 1922837 (The Pile)

Max Activating Token Index: 68

Text #14

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.8371. Min Act: -0.0000

Data Index: 1366365 (The Pile)

Max Activating Token Index: 305

Text #15

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.8292. Min Act: 0.0000

Data Index: 1466251 (The Pile)

Max Activating Token Index: 430

Text #16

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.9273. Min Act: -0.0000

Data Index: 1956940 (The Pile)

Max Activating Token Index: 519

Text #17

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.8387. Min Act: 0.0000

Data Index: 1332019 (The Pile)

Max Activating Token Index: 828

Text #18

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.8814. Min Act: -0.0000

Data Index: 492186 (The Pile)

Max Activating Token Index: 559

Text #19

Max Range: 1.2582. Min Range: -1.2582

Max Act: 0.8648. Min Act: 0.0000

Data Index: 816564 (The Pile)

Max Activating Token Index: 252